CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation
This addresses the challenge of stable and efficient continual learning for LLMs, though it is incremental as it builds on existing LoRA methods.
The paper tackles the problem of catastrophic forgetting and high parameter count in continual fine-tuning of large language models by introducing CURLoRA, which uses CUR matrix decomposition with LoRA, resulting in improved stability and performance across tasks while reducing trainable parameters.
This paper introduces CURLoRA, a novel approach to fine-tuning large language models (LLMs) that leverages CUR matrix decomposition in the context of Low-Rank Adaptation (LoRA). Our method addresses two critical challenges in LLM fine-tuning: mitigating catastrophic forgetting during continual learning and reducing the number of trainable parameters. We propose a unique modification to the CUR decomposition process, utilizing inverted probabilities for column and row selection which acts as an implicit regularization, and initializing the $U$ matrix as a zero matrix, and only fine-tuning it. We demonstrate through experiments on multiple datasets that CURLoRA outperforms standard LoRA in mitigating catastrophic forgetting. It maintains model stability and performance across tasks while significantly reducing the number of trainable parameters. Our results show that CURLoRA achieves very good and stable task accuracy while maintaining base model's perplexity scores fixed compared to LoRA upon continual fine-tuning, particularly in scenarios with limited data.